clinpubr: Clinical Publication

# install.packages("pak")
pak::pak("yotasama/clinpubr")

library(clinpubr)

# Sample messy data
messy_data <- data.frame(values = c("１２．３", "0..45", "  67 ", "", "ａｂａｎｄｏｎ"))
clean_data <- value_initial_cleaning(messy_data$values)
print(clean_data)
#> [1] "12.3"    "0.45"    "67"      NA        "abandon"

# Sample messy data
x <- c("1.2(XXX)", "1.5", "0.82", "5-8POS", "NS", "FULL")
print(check_nonnum(x))
#> [1] "1.2(XXX)" "5-8POS"   "NS"       "FULL"

# Sample messy data
x <- c("1.2(XXX)", "1.5", "0.82", "5-8POS", "NS", "FULL")
print(extract_num(x))
#> [1] 1.20 1.50 0.82 5.00   NA   NA

print(extract_num(x,
  res_type = "first", # Extract the first number
  multimatch2na = TRUE, # Convert illegal multiple matches to NA
  zero_regexp = "NEG|NS", # Convert "NEG" and "NS" (matched using regex) to 0
  max_regexp = "FULL", # Convert "FULL" (matched using regex) to some specified quantile
  max_quantile = 0.95
))
#> [1] 1.20 1.50 0.82   NA 0.00 1.47

data(cancer, package = "survival")

# Screening for potential findings with regression models in the cancer dataset
scan_result <- regression_scan(cancer, y = "status", time = "time", save_table = FALSE)
#> Taking all variables as predictors
knitr::kable(scan_result)

var_types <- get_var_types(mtcars, strata = "vs") # Automatically infer variable types
print(var_types)
#> $factor_vars
#> [1] "cyl"  "vs"   "am"   "gear"
#> 
#> $exact_vars
#> [1] "cyl"  "gear"
#> 
#> $nonnormal_vars
#> [1] "drat" "carb"
#> 
#> $omit_vars
#> NULL
#> 
#> $strata
#> [1] "vs"
#> 
#> attr(,"class")
#> [1] "var_types"

tables <- baseline_table(mtcars,
  var_types = var_types, contDigits = 1, save_table = FALSE,
  filename = "baseline.csv", seed = 1 # set seed for simulated fisher exact test
)
knitr::kable(tables$baseline) # Display the table

data(cancer, package = "survival")

# Performing cox regression, which is inferred by `y` and `time`
p <- rcs_plot(cancer, x = "age", y = "status", time = "time", covars = c("sex", "ph.karno"), save_plot = FALSE)
#> Warning in rcs_plot(cancer, x = "age", y = "status", time = "time", covars =
#> c("sex", : 1 incomplete cases excluded.
plot(p)

data(cancer, package = "survival")

# Generating interaction plot of both linear and RCS models
p <- interaction_plot(cancer,
  y = "status", time = "time", predictor = "age",
  group_var = "sex", save_plot = FALSE
)
plot(p$lin)

plot(p$rcs)

data(cancer, package = "survival")
cancer$dead <- cancer$status == 2 # Preparing a binary variable for logistic regression
cancer$`age per 1 sd` <- c(scale(cancer$age)) # Standardizing age

# Performing multivairate logistic regression
p1 <- regression_forest(cancer,
  model_vars = c("age per 1 sd", "sex", "wt.loss"), y = "dead",
  as_univariate = FALSE, save_plot = FALSE
)
plot(p1)

p2 <- regression_forest(
  cancer,
  model_vars = list(
    Crude = c("age per 1 sd"),
    Model1 = c("age per 1 sd", "sex"),
    Model2 = c("age per 1 sd", "sex", "wt.loss")
  ),
  y = "dead",
  save_plot = FALSE
)
plot(p2)

data(cancer, package = "survival")
# coxph model with time assigned
p <- subgroup_forest(cancer,
  subgroup_vars = c("age", "sex", "wt.loss"), x = "ph.ecog", y = "status",
  time = "time", covars = "ph.karno", ticks_at = c(1, 2), save_plot = FALSE
)
plot(p)

# Building models with example data
data(cancer, package = "survival")
df <- kidney
df$dead <- ifelse(df$time <= 100 & df$status == 0, NA, df$time <= 100)
df <- na.omit(df[, -c(1:3)])

model0 <- glm(dead ~ age + frail, family = binomial(), data = df)
model1 <- glm(dead ~ ., family = binomial(), data = df)
df$base_pred <- predict(model0, type = "response")
df$full_pred <- predict(model1, type = "response")

# Generating most of the useful plots and metrics for model comparison
results <- classif_model_compare(df, "dead", c("base_pred", "full_pred"), save_output = FALSE)
#> Assuming 'TRUE' is [Event] and 'FALSE' is [non-Event]

knitr::kable(results$metric_table)

plot(results$roc_plot)

plot(results$calibration_plot)

plot(results$dca_plot)

# Generating a dummy importance vector
set.seed(5)
dummy_importance <- runif(20, 0.2, 0.6)^5
names(dummy_importance) <- paste0("var", 1:20)

# Plotting variable importance, keeping only top 15 and splitting at 10
p <- importance_plot(dummy_importance, top_n = 15, split_at = 10, save_plot = FALSE)
plot(p)
#> Warning: Removed 1 row containing missing values or values outside the scale range
#> (`geom_bar()`).